def model():
print(os.path.exists(_COMPUTE_GRAPH_NAME))
return ModelDescriptor(
name='FaceRecognition',
input_shape=(1, 160, 160, 3),
input_normalizer=(127.5, 128),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def model_descriptor(graph_name):
# Face detection model has special implementation in VisionBonnet firmware.
# input_shape, input_normalizer, and compute_graph params have on effect.
return ModelDescriptor(name='MODEL' + graph_name,
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(graph_name))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--test_file', default=None, help='Path to test file.')
args = parser.parse_args()
model = ModelDescriptor(name=args.model_name,
input_shape=(1, 192, 192, 3),
input_normalizer=(0, 1),
compute_graph=utils.load_compute_graph(
args.model_path))
if args.test_file:
with ImageInference(model) as inference:
image = Image.open(args.test_file)
result = inference.run(image)
print(tensors_info(result.tensors))
return
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
print('#%05d (%5.2f fps): %s' %
(inference.count, inference.rate,
tensors_info(result.tensors)))
def model():
# Face detection model has special implementation in VisionBonnet firmware.
# input_shape, input_normalizer, and computate_graph params have on effect.
return ModelDescriptor(
name='FaceDetection',
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model_path',
required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument('--input_height',
type=int,
required=True,
help='Input height.')
parser.add_argument('--input_width',
type=int,
required=True,
help='Input width.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
args = parser.parse_args()
model = ModelDescriptor(
name='test_run_model',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
with PiCamera(sensor_mode=4, framerate=30) as camera:
with CameraInference(model) as camera_inference:
last_time = time.time()
for i, result in enumerate(camera_inference.run()):
output_tensor_str = [
'%s [%d elements]' % (k, len(v.data))
for k, v in result.tensors.items()
]
cur_time = time.time()
fps = 1.0 / (cur_time - last_time)
last_time = cur_time
print('%d-th inference, fps: %.1f FPS, %s' %
(i, fps, ','.join(output_tensor_str)))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--speed',
default=0.5,
type=float,
help='Reduction factor on speed')
args = parser.parse_args()
model = ModelDescriptor(name=args.model_name,
input_shape=(1, 192, 192, 3),
input_normalizer=(0, 1),
compute_graph=utils.load_compute_graph(
args.model_path))
left = Motor(PIN_A, PIN_B)
right = Motor(PIN_C, PIN_D)
print('spinning')
try:
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
data = [
tensor.data for _, tensor in result.tensors.items()
]
lspeed, rspeed = data[0]
print('#%05d (%5.2f fps): %1.2f/%1.2f' %
(inference.count, inference.rate, lspeed, rspeed))
if lspeed < 0:
left.reverse(-max(-1, lspeed) * args.speed)
else:
left.forward(min(1, lspeed) * args.speed)
if rspeed < 0:
right.reverse(-max(-1, rspeed) * args.speed)
else:
right.forward(min(1, rspeed) * args.speed)
except Exception as e:
left.stop()
right.stop()
print(e)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--input_height',
type=int,
required=True,
help='Input height.')
parser.add_argument('--input_width',
type=int,
required=True,
help='Input width.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
args = parser.parse_args()
model = ModelDescriptor(
name=args.model_name,
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
print('#%05d (%5.2f fps): %s' %
(inference.count, inference.rate,
tensors_info(result.tensors)))
def model():
return ModelDescriptor(
name='object_detection',
input_shape=(1, 256, 256, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def model(model_type):
this_model = _MODELS[model_type]
return ModelDescriptor(name=model_type,
input_shape=this_model.input_shape,
input_normalizer=this_model.input_normalizer,
compute_graph=this_model.compute_graph())
def model():
return ModelDescriptor(
name='DishDetection',
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
# for details about the parameters:
frameWidth = 256
frameHeight = 256
frameRate = 20
contrast = 40
rotation = 180
# Set the picamera parametertaob
camera = picamera.PiCamera()
camera.resolution = (frameWidth, frameHeight)
camera.framerate = frameRate
camera.contrast = contrast
model = ModelDescriptor(name="DarthVaderDetector",
input_shape=(1, 256, 256, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
os.path.join(os.getcwd(),
"darthvader.binaryproto")))
# Start the video process
with ImgCap(model, frameWidth, frameHeight, DEBUG) as img:
camera.start_recording(img, format='rgb', splitter_port=1)
try:
while True:
camera.wait_recording(
timeout=0
) # using timeout=0, default, it'll return immediately
# if img.output is not None:
# print(img.output[0,0,0])
except KeyboardInterrupt:
def model(model_type=MOBILENET):
return ModelDescriptor(name=model_type,
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
_COMPUTE_GRAPH_NAME_MAP[model_type]))
def model_roll():
return ModelDescriptor(name='roll_inference',input_shape=(1, 64, 64, 3),input_normalizer=(128, 128),compute_graph=utils.load_compute_graph(_ROLL_GRAPH_NAME))
def model():
return ModelDescriptor(
name='dish_classifier',
input_shape=(1, 192, 192, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument('--debug', default=False, action='store_true')
args = parser.parse_args()
DEBUG = args.debug
model = ModelDescriptor(
name=args.model_name,
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
# Start the video process
with ImgCap(model, frameWidth, frameHeight, DEBUG) as img:
camera.start_recording(img, format='rgb', splitter_port=1)
try:
while True:
camera.wait_recording(
timeout=0
) # using timeout=0, default, it'll return immediately
# if img.output is not None:
# print(img.output[0,0,0])
except KeyboardInterrupt:
def model():
return ModelDescriptor(
name='cifar10_classification',
input_shape=(1, 32, 32, 3),
input_normalizer=(127.5, 127.5),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
parser.add_argument('--label_path', required=True, help='Path to label file.')
parser.add_argument('--model_path', required=True, help='Path to model file.')
parser.add_argument('--input', required=True, help='Input height.')
parser.add_argument('--input_size',
type=int,
required=True,
help='Input height.')
parser.add_argument('--output_key', required=True)
args = parser.parse_args()
image = Image.open(args.input)
width, height = image.size
model = ModelDescriptor(name=args.model_name,
input_shape=(1, args.input_size, args.input_size, 3),
input_normalizer=(128, 128),
compute_graph=utils.load_compute_graph(
args.model_path))
inference = ImageInference(model)
if inference:
starttime = datetime.now()
result = inference.run(image)
deltatime = datetime.now() - starttime
print(
str(deltatime.seconds) + "s " + str(deltatime.microseconds / 1000) +
"ms")
assert len(result.tensors) == 1
tensor = result.tensors[args.output_key]
def model():
return ModelDescriptor(
name='image_classification',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model_path',
required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument(
'--label_path',
required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument(
'--input_height', type=int, required=True, help='Input height.')
parser.add_argument(
'--input_width', type=int, required=True, help='Input width.')
parser.add_argument(
'--input_layer', required=True, help='Name of input layer.')
parser.add_argument(
'--output_layer', required=True, help='Name of output layer.')
parser.add_argument(
'--num_frames',
type=int,
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument(
'--input_mean', type=float, default=128.0, help='Input mean.')
parser.add_argument(
'--input_std', type=float, default=128.0, help='Input std.')
parser.add_argument(
'--input_depth', type=int, default=3, help='Input depth.')
parser.add_argument(
'--threshold', type=float, default=0.6,
help='Threshold for classification score (from output tensor).')
parser.add_argument(
'--preview',
action='store_true',
default=False,
help='Enables camera preview in addition to printing result to terminal.')
parser.add_argument(
'--gpio_logic',
default='NORMAL',
help='Indicates if NORMAL or INVERSE logic is used in GPIO pins.')
parser.add_argument(
'--show_fps',
action='store_true',
default=False,
help='Shows end to end FPS.')
args = parser.parse_args()
# Model & labels
model = ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
with PiCamera() as camera:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
# Scaled and cropped resolution. If different from sensor mode implied
# resolution, inference results must be adjusted accordingly. This is
# true in particular when camera.start_recording is used to record an
# encoded h264 video stream as the Pi encoder can't encode all native
# sensor resolutions, or a standard one like 1080p may be desired.
camera.resolution = (1640, 1232)
# Start the camera stream.
camera.framerate = 30
camera.start_preview()
while True:
while True:
long_buffer = []
short_buffer = []
pinStatus(pin_A,'LOW',args.gpio_logic)
pinStatus(pin_B,'LOW',args.gpio_logic)
pinStatus(pin_C,'LOW',args.gpio_logic)
leds.update(Leds.rgb_on(GREEN))
face_box = detect_face()
print("Entered the loop of face classifier")
hand_box_params = determine_hand_box_params(face_box)
if image_boundary_check(hand_box_params):
print("Hand gesture identified")
break
# Start hand classifier
is_active = False
leds.update(Leds.rgb_on(PURPLE))
start_timer = time.time()
with ImageInference(model) as img_inference:
while True:
print("Entered the loop of gesture classifier")
#check_termination_trigger()
if is_active:
leds.update(Leds.rgb_on(RED))
hands_image = capture_hands_image(camera,hand_box_params)
output = classify_hand_gestures(img_inference,hands_image,model=model,labels=labels,output_layer=args.output_layer,threshold = args.threshold)
short_guess, num_short_guess = buffer_update(output,short_buffer,short_buffer_length)
long_guess, num_long_guess = buffer_update(output,long_buffer,long_buffer_length)
# Activation of classifier
if (long_guess == activation_index or long_guess == deactivation_index) and not is_active and num_long_guess >= (long_buffer_length - 3):
is_active = True
leds.update(Leds.rgb_on(RED))
send_signal_to_pins(activation_index,args.gpio_logic)
long_buffer = []
num_long_guess = 0
time.sleep(1)
# Deactivation of classifier (go back to stable face detection)
if (long_guess == activation_index or long_guess == deactivation_index) and is_active and num_long_guess >= (long_buffer_length - 3):
is_active = False
leds.update(Leds.rgb_off())
long_buffer = []
num_long_guess = 0
send_signal_to_pins(deactivation_index,args.gpio_logic)
time.sleep(1)
break
# If not activated within max_no_activity_period seconds, go back to stable face detection
if not is_active:
timer = time.time()-start_timer
if timer >= max_no_activity_period:
leds.update(Leds.rgb_off())
send_signal_to_pins(deactivation_index,args.gpio_logic)
time.sleep(1)
break
else:
start_timer = time.time()
# Displaying classified hand gesture commands
if num_short_guess >= (short_buffer_length-1) and is_active:
print_hand_command(short_guess)
send_signal_to_pins(short_guess,args.gpio_logic)
camera.stop_preview()
def main():
model_path = '/opt/aiy/models/retrained_graph.binaryproto'
#model_path = '/opt/aiy/models/mobilenet_v1_160res_0.5_imagenet.binaryproto'
label_path = '/opt/aiy/models/retrained_labels_new.txt'
#label_path = '/opt/aiy/models/mobilenet_v1_160res_0.5_imagenet_labels.txt'
model_path = '/opt/aiy/models/rg_v3_new.binaryproto'
label_path = '/opt/aiy/models/retrained_labels_new.txt'
input_height = 160
input_width = 160
input_layer = 'input'
output_layer = 'final_result'
threshold = 0.8
# Model & labels
model = ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, input_height, input_width, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(model_path))
labels = read_labels(label_path)
new_labels = []
for eachLabel in labels:
if len(eachLabel)>1:
new_labels.append(eachLabel)
labels = new_labels
#print(labels)
s = xmlrpc.client.ServerProxy("http://aiy.mdzz.info:8000/")
player = TonePlayer(BUZZER_GPIO, 10)
player.play(*MODEL_LOAD_SOUND)
while True:
while True:
if s.camera() == 1:
print('vision kit is woken up')
with Leds() as leds:
leds.pattern = Pattern.blink(100)
leds.update(Leds.rgb_pattern(Color.RED))
time.sleep(2.0)
start_time = round(time.time())
break
time.sleep(0.2)
print('no signal, sleeping...')
with PiCamera() as camera:
# Configure camera
camera.sensor_mode = 4
camera.resolution = (1664, 1232) # Full Frame, 16:9 (Camera v2)
camera.framerate = 30
camera.start_preview()
while True:
# Do inference on VisionBonnet
#print('Start capturing')
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
#print(type(result))
faces = face_detection.get_faces(result)
if len(faces) >= 1:
#print('camera captures...')
extension = '.jpg'
filename = time.strftime('%Y-%m-%d %H:%M:%S') + extension
camera.capture(filename)
image_npp = np.empty((1664 * 1232 * 3,), dtype=np.uint8)
camera.capture(image_npp, 'rgb')
image_npp = image_npp.reshape((1232, 1664, 3))
image_npp = image_npp[:1232, :1640, :]
# image = Image.open('jj.jpg')
# draw = ImageDraw.Draw(image)
faces_data = []
faces_cropped = []
for i, face in enumerate(faces):
# print('Face #%d: %s' % (i, face))
x, y, w, h = face.bounding_box
#print(x,y,w,h)
w_rm = int(0.3 * w / 2)
face_cropped = crop_np((x, y, w, h), w_rm, image_npp)
if face_cropped is None: continue #print('face_cropped None'); continue
# faces_data.append(image[y: y + h, x + w_rm: x + w - w_rm])
# image[y: y + h, x + w_rm: x + w - w_rm].save('1.jpg')
face_cropped.save('face_cropped_'+str(i)+'.jpg')
faces_cropped.append(face_cropped)
#break
break
# else:
# tt = round(time.time()) - start_time
# if tt > 10:
# break
#print('face cutting finishes')
#print(type(faces_cropped), len(faces_cropped))
player.play(*BEEP_SOUND)
flag = 0
for eachFace in faces_cropped:
#print(type(eachFace))
if eachFace is None: flag = 1
if (len(faces_cropped)) <= 0: flag = 1
if flag == 1: continue
with ImageInference(model) as img_inference:
#with CameraInference(model) as img_inference:
print('Entering classify_hand_gestures()')
output = classify_hand_gestures(img_inference, faces_cropped, model=model, labels=labels,
output_layer=output_layer, threshold=threshold)
#print(output)
if (output == 3):
player.play(*JOY_SOUND)
print('Yani face detected')
print(s.result("Owner", filename))
else:
player.play(*SAD_SOUND)
print('Suspicious face detected')
print(s.result("Unknown Face", filename))
upload(filename)
# Stop preview #
#break
while (s.camera()==0):
print('sleeping')
time.sleep(.2)
print('Waken up')